Skip to content
Date and source

Dates follow the news timeline in Beijing time and include both endpoints.

Oct 22Thu
  1. Pictory 官方博客55

    Pictory releases Pictory 3, adding an AI video agent

    Pictory releases Pictory 3, adding an AI video agent: users describe their video requirements and answer five setup questions, after which the agent generates a script, scenes and a preview, and then generates the final video after revisions via conversation or the editor. Videos can start from an idea, script, webpage, document, PowerPoint or recording, with documents and URLs combined limited to at most 5 sources each time. New users will be moved into Pictory 3 with the rollout, while old projects remain in Projects and will not be converted automatically.

  2. Luma News48

    Ray 3.2 vs Seedance 2.5: Which Luma model is better suited for your project?

    Luma's Ray 3.2 and Seedance 2.5 focus on frame-level control and synchronized audio generation, respectively, allowing users to choose based on project needs. Ray 3.2 supports HDR output, EXR export, and up to 16 keyframes, making it suitable for professional post-production; Seedance 2.5 can generate 30-second clips with synchronized sound effects, music, and lip sync in one go. Both are available through Luma and can be switched within the same workspace.

  3. Luma News16

    Gemini Omni Flash vs. Wan 3.0: Which Is Currently the Best AI Video Model?

    Gemini Omni Flash excels at conversational editing and multimodal input. Wan 3.0 can generate clips up to 30 seconds long and supports document input. Both have their own advantages. Luma AI's Ray 3.2 offers multi-keyframe sequences, HDR output, and EXR export. Layers (powered by Uni-1) supports single-element modification, making it suitable for production workflows. In 2025, the AI video generation market size is approximately $700 million to $2 billion, with North America leading.

  4. Higgsfield 官方博客67

    Kling 4.0 launches on Higgsfield: supports 30-second generation and 10 keyframes

    Kling 4.0 is now available on Higgsfield AI, with single-generation duration extended from Kling 3.0's 3 to 15 seconds to 3 to 30 seconds, up to 1080p with dual-channel stereo.

    Why it matters: Compared with Kling 3.0, it lists upgrades in duration, keyframes, reference materials, and audio, and gives credit costs for each resolution to help assess integration costs.

  5. Krea 官方博客58

    Krea releases Illustrator plugin that can generate images within documents and convert them to vector paths

    Krea released an Illustrator plugin that can generate images within an Illustrator document, then use Image Trace to convert them into editable vector paths. The plugin supports sending selections or artboards back to Krea for modification and placing them back in place; Krea Agent can draw shapes, typeset text, and organize layers and artboards within the document.

  6. Krea 官方博客62

    Krea launches After Effects plugin that can generate footage and background plates within compositions

    Krea released an After Effects plugin that generates motion concepts, background plates and coherent shot footage within the panel, with results entering the current composition as standard media assets. The plugin supports After Effects 2025 and above, macOS 12 or Windows 10 and above; generation runs on Krea servers and requires account login and internet connection; the panel has built-in Krea Realtime preview, and the free plan includes 100 compute units per day.

    Why it matters: Krea brings image generation into the After Effects panel, letting motion designers generate images within compositions and use them directly as assets.

Oct 21Wed
  1. Higgsfield 官方博客38

    A hands-on comparison of the top ten AI video generators in 2026: Higgsfield, Runway, Kling, and more

    Higgsfield ranks first in the 2026 comparison of the top ten AI video generators, integrating 35+ models and tools for character consistency, ad production, and agent capabilities into one subscription. Runway focuses on editing and VFX workflows with Gen-4.5, the official Kling app offers direct access to Kling 3.0/4.0, and Google Flow offers Veo 3.1 starting at $4.99. All platform prices and quotas were verified in October 2026.

  2. 可灵官方博客33

    What Is Lip Sync? Meaning and an Analysis of Lip-Sync Technology in AI Video

    Kling AI's Lip Sync tool can add speech or singing to an existing character video and align the lip movements, while Kling 4.0 can simultaneously produce dialogue, facial performance, and sound when generating new scenes. Compared with the previous generation, Kling 4.0 improves lip sync, supports more flexible voice references, expands multilingual dialogue, and adds dual-channel stereo, with audio and visuals generated in sync by default.

  3. 可灵官方博客25

    How to Edit Photos with Kling IMAGE 3.0 Omni: A Beginner's Guide

    This guide first covers the three steps of traditional photo editing (cropping and level correction; adjusting exposure/shadows/highlights/white balance/contrast/saturation; exporting JPEG/PNG/WebP), then explains how AI photo editing uses natural-language descriptions to replace objects, change outfits, change backgrounds, and change styles. Kling IMAGE 3.0 Omni supports image-to-image workflows, can combine up to 10 reference images, and natively outputs 2K and 4K.

  4. fal 官方博客28

    EAGLE-4 technical deep dive: Fireworks and fal release speculative decoding benchmark dataset

    Fireworks and fal jointly released a technical analysis of EAGLE-4 and Prompt Enhancement SpecBench, a speculative decoding benchmark dataset for creative tasks. The dataset contains 400 samples, covering 100 each of text-to-video, image-to-video, text-to-image and image-to-image. On Qwen 3.8 27B, EAGLE-4 uses sliding window attention and a low-rank candidate head to reduce draft cost, and the verification tree dynamically adjusts width and depth based on GPU latency measurements.

  5. Krea 官方博客62

    Krea 3 vs Nano Banana Pro: leads on leaderboards, but still behind on 4K and long text

    Krea officially compared Krea 3 with Nano Banana Pro, stating that Krea 3 ranks higher on all three leaderboards—Arena Multi-Image Edit, Design Arena and Artificial Analysis—that most edits return within 8 seconds at native 2K, and that it is 3 times cheaper than GPT Image 2 and Nano Banana Pro.

    Why it matters: Krea officially compared its own Krea 3 with Nano Banana Pro using three public leaderboards and same-prompt tests, and listed the applicable scenarios for each.

  6. FastVideo 视频模型 · 模型发布80

    FastVideo releases ComfyUI version model weights for FastH3 Omni

    FastVideo released ComfyUI-usable weights for the final version of FastH3 Omni, providing two diffusion models, BF16 and INT8 ConvRot, which can generate video and synchronized audio from prompts and ordered image, video, and audio references.

    Why it matters: FastH3 Omni releases ComfyUI-usable BF16 and INT8 weights and provides the way to connect reference images, video, and audio, making it easier for creators to evaluate local video production pipelines.

  7. Krea 官方博客60

    Krea 3 appears on three image-editing leaderboards: a breakdown of each ranking and interval

    Krea 3 Ultra ranked 4th in Arena multi-image editing, 8th in single-image editing, 5th in Artificial Analysis AA-Image-Editing v2.1, and 4th in Design Arena (out of 51 models) on three image-editing leaderboards published on October 19-20.

    Why it matters: Krea officially breaks down the votes, confidence intervals, and ranking intervals of the three leaderboards item by item, explaining why the same model appears in four positions.

Oct 20Tue
  1. Higgsfield 官方博客22

    How to make AI real estate videos from photos: a hands-on guide to Higgsfield Cinema Studio 4.0

    Higgsfield released a tutorial on how to use Cinema Studio 4.0 to turn real estate photos into video clips of each space one by one, then stitch them into a property tour with listing information and music. The workflow includes uploading clear photos as references, setting camera/lens/aperture/lighting/pacing in the Director's Panel, choosing one gentle movement per clip from 30+ camera movement presets, and using Extend and Edit Video to fix the results.

  2. 可灵官方博客38

    20 video ideas for Kling 4.0: lifestyle, tutorial, and story topics for content creators

    Kling 4.0 supports text-to-video and image-to-video, with a single clip up to 30 seconds long, maintaining more stable imagery during large movements and complex camera work. Its Omni Reference can combine up to 15 image, video, and sound references plus Elements, and can additionally use up to 10 uploaded images as keyframes to control shot nodes. Officially, 20 video idea examples are provided around directions such as daily life, tutorials, personal stories, hobbies, and festivals.

  3. 可灵官方博客38

    How to improve video quality? Kling AI provides a repair guide for blur, noise, and other issues

    Kling AI has released a video quality improvement guide, giving corresponding repair methods for issues such as insufficient lighting, noise, compression artifacts, blur, poor composition, and incomplete motion. Using Kling VIDEO 3.0 Omni, users can upload 3–10 second videos, adjust lighting, color, background, and composition via prompts while preserving the original motion, and choose 1080p or 4K output. The guide also gives quality optimization suggestions separately for social short videos, YouTube long videos, and old footage.

  4. 可灵官方博客38

    How to bring old photos to life with Kling 4.0: a step-by-step AI guide

    Kling 4.0 supports 3–30 second video generation, and its Omni Reference can take up to 15 reference materials (including up to 10 images) to maintain character face and clothing consistency in old photo animation. The model strengthens large-motion stability, making actions such as waving, taking a few steps, and turning more natural, and Keyframes mode can use up to 10 keyframe images to control scene transitions.

  5. 可灵官方博客31

    What is AI art, and how to create your own works with Kling AI

    Kling AI has released a guide on how to generate AI artworks from text or images using Kling IMAGE 3.0 and IMAGE 3.0 Omni. IMAGE 3.0 supports up to 10 reference images and allows fine-tuning of details with natural language instructions; IMAGE 3.0 Omni's Image Series mode can maintain character and style consistency across multiple illustrations and natively outputs 2K/4K.

  6. Kapwing 创作指南69

    How to build an AI film workflow with GPT-6 Astra, Blender, and Seedance 2.5

    Kapwing released a tutorial demonstrating using GPT-6 Astra to connect with Blender to build a dragon and scene's gray model, animation and camera shots, then using GPT Image 2 to generate design drawings and a photorealistic first frame, and finally Seedance 2.5 to generate a 10-second continuous shot.

    Why it matters: The author tested using GPT-6 Astra to drive Blender to build a 3D scene, then went through image-to-3D and Seedance 2.5 to produce the video, and listed a comparison of three 3D models and itemized costs.

  7. Kapwing 创作指南73

    How to use Seedance 2.5 to turn a single piece of footage into 4 camera angles

    Kapwing released a tutorial introducing the use of Claude skills to generate camera instruction prompts, then using Seedance 2.5 in Kai to reshoot a single fixed-camera piece of footage into a multi-camera edit.

    Why it matters: The author tested single-camera to multi-camera conversion with Seedance 2.5, providing the complete prompt and failure cases, which can be transferred to multi-camera editing for short dramas.